Inspect before downloading
See what is inside
These previews come from the published bundle files, so you can judge the method and writing before using it.
Role guide
Data Scientist Source-Aware Guide
Defines source-aware data-science study design, modeling, validation,
Read the fileOverview
Data Scientist overview
Use this bundle to prepare source-aware data-science study design, modeling, validation, and deployment review and a review-ready data science analysis brief.
Read the fileWorkflow
Data Scientist source-aware triage
1. State the requested decision or artifact. 2. Inventory evidence: question, population, decision, and success criteria; data provenance, consent, lineage, definitions, and access; code.
Read the fileTemplate
data science analysis brief
Review-ready artifact for data-science study design, modeling, validation,
Read the fileIs this bundle right for your task?
Who it is for
- People performing or supporting Data Scientist work, plus teams reviewing its decisions and outputs
- Teams working in Data and analytics, Research
When to use it
- A Data Scientist task needs a structured plan, evidence checklist, or review-ready output.
- A recommendation needs its assumptions, owners, risks, dependencies, and success measures made explicit.
What you need to provide
- The task objective, intended audience, working context, constraints, source material, and decision owner.
- Relevant reports, exports, examples, policies, prior decisions, and success measures available for the task.
Tasks and expected outputs
Questions it helps answer
- Prepare a data science analysis brief without fabricating local facts.
- Separate verified, provided, assumed, and missing evidence.
- Produce a review-ready recommendation with explicit verification and approval boundaries.
What it helps produce
- data science analysis brief
Practical example
Use it with an agent
Load the bundle as context, provide the evidence named above, then adapt this example to your situation.
Provide the task objective, intended audience, working context, constraints, source material, and decision owner. Ask the agent to approach Data Scientist work by producing data science analysis brief with a prioritized plan, evidence checks, owners, risks, and unresolved questions. Begin with O*NET OnLine — Summary / 15 2051.00, then confirm that the reference is current and applicable. Inspect Data Scientist Source-Aware Guide before drafting.
Context path: bundles/roles/data-scientist
What the bundle includes
Frameworks
- source-evidence matrix
- data-science study design, modeling, validation, and deployment review matrix
- qualified-review gate
Evaluations
- Data Scientist source-awareness check
Sources used to build this bundle
These are the public references behind the role definition and operating guidance. The bundle does not replace current documentation or evidence from your site.
Limitations and safe use
Do not use this for
- Treating the bundle as a substitute for organization-specific authority, firsthand evidence, or accountable review.
Known limitations
- Use the cited authoritative sources for general role, standards, or regulatory context; local facts, records, values, states, and permissions require inspected evidence.
- Task-specific work requires current evidence for question, population, decision, and success criteria; data provenance, consent, lineage, definitions, and access; code, environment, methods, assumptions, train-test split, and leakage controls; metrics, uncertainty, subgroup analysis, privacy, security, deployment, and monitoring evidence.
- Do not infer data fitness, causality, model performance, fairness, generalization, or production behavior.
Safety notes
- Minimize personal, customer, employee, financial, credential, security, privileged, health, and other sensitive data.
- Require explicit confirmation before actions that access sensitive data, deploy a model, set a decision threshold, or claim causal, fair, safe, or compliant performance.
- Route legal, privacy, security, compliance, financial, employment, clinical, safety, and other qualified judgments to an evidenced accountable reviewer.